AI agents use update-card to create or update resources in Clanki — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Clanki environment.
This tool modifies flashcard data reversibly — updates can be undone or corrected later. It does not delete data permanently (which would be Destructive) nor execute arbitrary code. The medium severity reflects that an AI agent could overwrite flashcard content unintentionally, but the impact is limited to a single user's study material and recoverable.
From the tool's definition The tool name is 'update-card' and the description states 'Update an existing flashcard', which indicates it modifies existing data.
Documented attack patterns abuse exactly the kind of access update-card gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Clanki, and nothing reaches the server without passing your rules. This is the rule we recommend for update-card:
{
"version": "1",
"default": "deny",
"tools": {
"update-card": {
"limits": [
{
"counter": "update-card_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-card stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing flashcard. It is categorised as a Write tool in the Clanki MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Clanki MCP server in PolicyLayer and add a rule for update-card: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Clanki. Nothing to install.
update-card is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update-card rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for update-card. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
update-card is provided by the Clanki MCP server (jasperket/clanki). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Clanki, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Clanki tools catalogued and risk-classified — across an index of 43,000+ MCP servers.